Start Building with TokenLabs

Production-ready inference endpoints powered by NVIDIA DGX Spark. OpenAI-compatible API.

🔍
-
Models
—
From / 1M Input

Inference Endpoints

Select a model to view pricing, try the playground, or grab API code.

Loading models...

Recent Run

Latest overnight observability run results

2026-04-15 · Observability Run
Overnight Observability Run — 15 Tasks
DCGM, OTel, SLO, and failure simulation on DGX Spark GB10. Top finding: chunked prefill is the highest-leverage fix for 44.8s TTFT p95.
SLO Tier 1 ✓ E2E Traces ✗ TTFT p95 44.8s
Overview
Playground
API Reference
Model Specifications
Pricing · per token
Input tokens
per 1M tokens
$0.00
Cached input tokens
per 1M tokens
$0.0000
Output tokens
per 1M tokens
$0.00

Prices derived from CI benchmarks (vLLM on DGX Spark).

Quick links
📈Grafana Monitoring→ 🔗GitHub Repository→
API base URL

Compatible with openai, litellm, langchain.

All Available Models
Model
Primary
System Prompt
Parameters
Temperature0.70
Max Tokens512
Top P1.00
Options
Streaming
Mode: Select a model to compare
💬
Start a conversation
Send a message to chat with the selected model.
Quantization benefits
LLM haiku
FP8 vs NVFP4
About DGX Spark
OpenAI-compatible API
Endpoint
POST

OpenAI-compatible chat completions. Streaming via stream: true.

Model identifier
Code Examples
cURL
Python
Node.js
LiteLLM

          

          

          

        

      

      

        
Request Parameters

        

          

            

              Parameter
              Type
              Description
            

            
              
modelstringFull model identifier

              
messagesarrayArray of {role, content} objects

              
max_tokensintegerMax tokens to generate (default 512)

              
temperaturefloatSampling temperature 0–2 (default 0.7)

              
top_pfloatNucleus sampling (default 1.0)

              
streambooleanStream via SSE (default false)